
import warnings
from scipy import stats
from pycountry_convert import country_alpha2_to_continent_code, country_name_to_country_alpha2
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.model_selection import RandomizedSearchCV
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.model_selection import cross_val_score
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.ensemble import RandomForestRegressor
from pprint import pprint
from sklearn.metrics import r2_score
import seaborn as sns
import plotly.express as px
import matplotlib.pyplot as plt
%matplotlib inline


#sns.set_theme(context='notebook', style='darkgrid', palette='deep', font='sans-serif', color_codes=True, rc=None)
warnings.filterwarnings("ignore", category=DeprecationWarning)
pd.options.mode.chained_assignment = None


life_expectancy_data = pd.read_csv('Life Expectancy Data.csv')
life_expectancy_data.head()


pd.set_option('display.max_columns', None) 
life_expectancy_data.columns=['Country', 'Year', 'Status', 'Life Expectancy ', 'Adult Mortality',
       'Infant Deaths', 'Alcohol', 'Percent Expenditure', 'Hep B',
       'Measles', 'BMI', 'U-5 Deaths', 'Polio', 'Total Expenditure',
       'Diphtheria', 'HIVAIDS','GDP', 'Population', 'Thinness 10-19',
       'Thinness 5-9', 'Income Composition', 'Schooling']
#Canada and France are mislabeled as Developing
life_expectancy_data[life_expectancy_data['Country']=='France']['Status'].replace('Developing','Developed')
life_expectancy_data[life_expectancy_data['Country']=='Canada']['Status'].replace('Developing','Developed')
life_expectancy_data.head(10)


import missingno as msno
print(msno.matrix(life_expectancy_data))
life_expectancy_data.describe()

AxesSubplot(0.125,0.11;0.698618x0.77)


life_expectancy_data.head().T


# Filling Missing Values
life_expectancy_data= life_expectancy_data.fillna(life_expectancy_data.mean())

C:\Users\HP\Anaconda3\lib\site-packages\ipykernel_launcher.py:2: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.


life_expectancy_data.isnull().sum()

Country                0
Year                   0
Status                 0
Life Expectancy        0
Adult Mortality        0
Infant Deaths          0
Alcohol                0
Percent Expenditure    0
Hep B                  0
Measles                0
BMI                    0
U-5 Deaths             0
Polio                  0
Total Expenditure      0
Diphtheria             0
HIVAIDS                0
GDP                    0
Population             0
Thinness 10-19         0
Thinness 5-9           0
Income Composition     0
Schooling              0
dtype: int64


life_expectancy_data.describe(include='all')


life_expectancy_data['Population'] = life_expectancy_data['Population']/1000000
life_expectancy_data


life_expectancy_data = life_expectancy_data.dropna(axis=0)
life_expectancy_data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 2938 entries, 0 to 2937
Data columns (total 22 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Country              2938 non-null   object 
 1   Year                 2938 non-null   int64  
 2   Status               2938 non-null   object 
 3   Life Expectancy      2938 non-null   float64
 4   Adult Mortality      2938 non-null   float64
 5   Infant Deaths        2938 non-null   int64  
 6   Alcohol              2938 non-null   float64
 7   Percent Expenditure  2938 non-null   float64
 8   Hep B                2938 non-null   float64
 9   Measles              2938 non-null   int64  
 10  BMI                  2938 non-null   float64
 11  U-5 Deaths           2938 non-null   int64  
 12  Polio                2938 non-null   float64
 13  Total Expenditure    2938 non-null   float64
 14  Diphtheria           2938 non-null   float64
 15  HIVAIDS              2938 non-null   float64
 16  GDP                  2938 non-null   float64
 17  Population           2938 non-null   float64
 18  Thinness 10-19       2938 non-null   float64
 19  Thinness 5-9         2938 non-null   float64
 20  Income Composition   2938 non-null   float64
 21  Schooling            2938 non-null   float64
dtypes: float64(16), int64(4), object(2)
memory usage: 527.9+ KB


Eswatini =life_expectancy_data[life_expectancy_data['Country'] == 'Swaziland']
Eswatini


life_expectancy_data.columns

Index(['Country', 'Year', 'Status', 'Life Expectancy ', 'Adult Mortality',
       'Infant Deaths', 'Alcohol', 'Percent Expenditure', 'Hep B', 'Measles',
       'BMI', 'U-5 Deaths', 'Polio', 'Total Expenditure', 'Diphtheria',
       'HIVAIDS', 'GDP', 'Population', 'Thinness 10-19', 'Thinness 5-9',
       'Income Composition', 'Schooling'],
      dtype='object')


plt.plot(Eswatini['Year'], Eswatini['Life Expectancy '], color='red')
plt.xlabel('Year')
plt.ylabel('Life Expectancy ')
plt.title("Swaziland")
plt.show()


plt.boxplot([life_expectancy_data[life_expectancy_data['Status']=='Developing']['Life Expectancy '], life_expectancy_data[life_expectancy_data['Status']=='Developed']['Life Expectancy ']], labels=['Developing','Developed'])
plt.ylabel('Life Expectancy ')
plt.xlabel('Countries')
plt.show()


life_expectancy_data.sort_values("Life Expectancy ")


life_expectancy_data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 2938 entries, 0 to 2937
Data columns (total 22 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Country              2938 non-null   object 
 1   Year                 2938 non-null   int64  
 2   Status               2938 non-null   object 
 3   Life Expectancy      2938 non-null   float64
 4   Adult Mortality      2938 non-null   float64
 5   Infant Deaths        2938 non-null   int64  
 6   Alcohol              2938 non-null   float64
 7   Percent Expenditure  2938 non-null   float64
 8   Hep B                2938 non-null   float64
 9   Measles              2938 non-null   int64  
 10  BMI                  2938 non-null   float64
 11  U-5 Deaths           2938 non-null   int64  
 12  Polio                2938 non-null   float64
 13  Total Expenditure    2938 non-null   float64
 14  Diphtheria           2938 non-null   float64
 15  HIVAIDS              2938 non-null   float64
 16  GDP                  2938 non-null   float64
 17  Population           2938 non-null   float64
 18  Thinness 10-19       2938 non-null   float64
 19  Thinness 5-9         2938 non-null   float64
 20  Income Composition   2938 non-null   float64
 21  Schooling            2938 non-null   float64
dtypes: float64(16), int64(4), object(2)
memory usage: 527.9+ KB


#Countries with the Highest Life Expectancy
country_vs_life = life_expectancy_data.groupby('Country', as_index = False)['Life Expectancy '].mean()
country_vs_life.sort_values(by = 'Life Expectancy ', ascending = False).head(10)


#Countries with the Lowest Life Expectancy
country_vs_life.sort_values(by = 'Life Expectancy ', ascending = True).head(10)


sns.lineplot(life_expectancy_data['Life Expectancy '])
plt.show()


life_expectancy_data['Country'].value_counts()

Afghanistan              16
Peru                     16
Nicaragua                16
Niger                    16
Nigeria                  16
                         ..
Niue                      1
San Marino                1
Nauru                     1
Saint Kitts and Nevis     1
Dominica                  1
Name: Country, Length: 193, dtype: int64


#Life Expectancy 
sns.distplot(life_expectancy_data['Life Expectancy '])
plt.axvline(life_expectancy_data['Life Expectancy '].mean(),0,.6,color='black')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()+life_expectancy_data['Life Expectancy '].std(),0,.45,color='black',linestyle='--')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()-life_expectancy_data['Life Expectancy '].std(),0,.45,color='black',linestyle='--')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()+2*life_expectancy_data['Life Expectancy '].std(),0,.30,color='black',linestyle='--')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()-2*life_expectancy_data['Life Expectancy '].std(),0,.30,color='black',linestyle='--')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()-3*life_expectancy_data['Life Expectancy '].std(),0,.15,color='black',linestyle='--')
sns.set(rc={'figure.figsize':(10,10)})
plt.show()

#QQ plot   
stats.probplot(life_expectancy_data['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy QQ Plot')
plt.show()
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))

C:\Users\HP\Anaconda3\lib\site-packages\ipykernel_launcher.py:2: UserWarning: 

`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

ShapiroResult(statistic=0.9563312530517578, pvalue=8.011480975249593e-29)


#Life Expectancy 
sns.distplot(life_expectancy_data[life_expectancy_data['Status']=='Developed']['Life Expectancy '])
sns.distplot(life_expectancy_data[life_expectancy_data['Status']=='Developing']['Life Expectancy '],color='y')
labels=['Developed','Developing']
plt.legend(labels=labels,bbox_to_anchor=(1.02, 1), loc=2, borderaxespad=0.)
sns.set(rc={'figure.figsize':(10,10)})
plt.show()

#QQ plot   
stats.probplot(life_expectancy_data[life_expectancy_data['Status']=='Developed']['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy Developed Countries QQ Plot')
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))
plt.show()
#QQ plot   
stats.probplot(life_expectancy_data[life_expectancy_data['Status']=='Developing']['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy Developing Countries QQ Plot')
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))
plt.show()

life_expectancy_data['Life Expectancy '].groupby(life_expectancy_data['Status']).describe()

C:\Users\HP\Anaconda3\lib\site-packages\ipykernel_launcher.py:2: UserWarning: 

`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

  
C:\Users\HP\Anaconda3\lib\site-packages\ipykernel_launcher.py:3: UserWarning: 

`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

  This is separate from the ipykernel package so we can avoid doing imports until

ShapiroResult(statistic=0.9563312530517578, pvalue=8.011480975249593e-29)

ShapiroResult(statistic=0.9563312530517578, pvalue=8.011480975249593e-29)


bins=[36,60,78,90]
labels=[3,2,1]
life_expectancy_data['world']=pd.cut(life_expectancy_data['Life Expectancy '],bins=bins,labels=labels)


#Life Expectancy 
sns.distplot(life_expectancy_data[life_expectancy_data['world']==1]['Life Expectancy '])
sns.distplot(life_expectancy_data[life_expectancy_data['world']==2]['Life Expectancy '],color='y')
sns.distplot(life_expectancy_data[life_expectancy_data['world']==3]['Life Expectancy '],color='r')

labels=['1st World','2nd World','3rd World']
plt.legend(labels=labels,bbox_to_anchor=(1.02, 1), loc=2, borderaxespad=0.)
sns.set(rc={'figure.figsize':(10,10)})
plt.show()

#QQ plot   
stats.probplot(life_expectancy_data[life_expectancy_data['world']==1]['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy 1st World Countries QQ Plot')
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))
plt.show()
#QQ plot   
stats.probplot(life_expectancy_data[life_expectancy_data['world']==2]['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy 2nd World Countries QQ Plot')
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))
plt.show()

stats.probplot(life_expectancy_data[life_expectancy_data['world']==3]['Life Expectancy '], dist="norm", plot=plt)
plt.title('Life Expectancy 3rd World Countries QQ Plot')
print(stats.shapiro(life_expectancy_data['Life Expectancy ']))
plt.show()

life_expectancy_data['Life Expectancy '].groupby(life_expectancy_data['world']).describe()

(0.9639620780944824, 7.816321706167366e-20)

(0.9639620780944824, 7.816321706167366e-20)

(0.9639620780944824, 7.816321706167366e-20)


LEcountry=life_expectancy_data.groupby(life_expectancy_data['Country'])['Life Expectancy '].mean().sort_values(kind="quicksort",ascending=False)
sns.pointplot(y='Country',x='Life Expectancy ',hue='Status',data=life_expectancy_data,order=LEcountry.index,join=True)
plt.title( 'Life Expectancy by Country')
plt.axvline(78,0,10,color='g')
plt.axvline(life_expectancy_data['Life Expectancy '].mean()-life_expectancy_data['Life Expectancy '].std(),0,10,color='r')
sns.set(rc={'figure.figsize':(20,40)})
plt.show()


sns.countplot(life_expectancy_data['Status'])
print('Developed or Developing Country Status')
print(life_expectancy_data.Status.value_counts()/len(life_expectancy_data.Status))
sns.set(rc={'figure.figsize':(10,10)})
plt.show()

sns.countplot(life_expectancy_data['world'])
print('1st,2nd,and 3rd World Countries')
print(((life_expectancy_data.world.value_counts()/len(life_expectancy_data.world))*193).round(0))
sns.set(rc={'figure.figsize':(10,10)})
plt.show()

Developed or Developing Country Status
Developing    0.853244
Developed     0.146756
Name: Status, dtype: float64

1st,2nd,and 3rd World Countries
2    133.0
3     34.0
1     26.0
Name: world, dtype: float64


def LEfactorplot(column):
    x=life_expectancy_data[life_expectancy_data['Status']=='Developed'][column]
    y=life_expectancy_data[life_expectancy_data['Status']=='Developed']['Life Expectancy ']
    x1=life_expectancy_data[life_expectancy_data['Status']=='Developing'][column]
    y1=life_expectancy_data[life_expectancy_data['Status']=='Developing']['Life Expectancy ']
    #Fit Lines
    z1 =np.polyfit(x,y,1)
    z2 =np.polyfit(x1,y1,1)
    z1poly = np.poly1d(z1) 
    z2poly = np.poly1d(z2)

    #Plot
    plt.scatter(x,y,alpha=1)
    plt.scatter(x1,y1,alpha=1)
    plt.plot(x,z1poly(x),linewidth=7.0)
    plt.plot(x1,z2poly(x1),linewidth=7.0,color='r')
    labels=['Developed','Developing']
    plt.legend(labels=labels,bbox_to_anchor=(1.02, 1), loc=2, borderaxespad=0.)
    plt.ylabel('Life Expectancy ')
    plt.xlabel(column)
LEfactorplot('Year')
plt.xticks(np.arange(2000,2016,1))
plt.show()


corrmat = life_expectancy_data.corr()
mask = np.zeros_like(corrmat, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
top_corr_features = corrmat.index
plt.figure(figsize=(15,15))
#plot heat map
sns.heatmap(life_expectancy_data[top_corr_features].corr(),annot=True,mask=mask)
sol = (corrmat.where(np.triu(np.ones(corrmat.shape), k=1).astype(np.bool))
                 .stack().sort_values(kind="quicksort",ascending=False))
LE=pd.Series(corrmat.unstack()[18:36]).sort_values(kind="quicksort",ascending=False)
print('Correlation Values for the {} countries left after Data Cleaning:'.format(len(life_expectancy_data['Country'].unique())))
LE[1:18]

Correlation Values for the 133 countries left after Data Cleaning:

Life Expectancy   BMI                    0.542042
                  GDP                    0.441322
                  Percent Expenditure    0.409631
                  Alcohol                0.402718
                  Diphtheria             0.341331
                  Polio                  0.327294
                  Hep B                  0.199935
                  Total Expenditure      0.174718
Year              Income Composition     0.122892
                  Schooling              0.088732
Life Expectancy   Year                   0.050771
                  Population            -0.022305
                  Measles               -0.068881
                  Infant Deaths         -0.169074
                  U-5 Deaths            -0.192265
                  HIVAIDS               -0.592236
                  Adult Mortality       -0.702523
dtype: float64


print('Top 10 Correlated Features Pairs:')
print(sol[0:10],'\n')
print('Bottom 10 Correlated Features Pairs:')
print(sol[143:153])

Top 10 Correlated Features Pairs:
Infant Deaths        U-5 Deaths            0.996906
Percent Expenditure  GDP                   0.959299
Thinness 10-19       Thinness 5-9          0.927913
Income Composition   Schooling             0.784741
Life Expectancy      Schooling             0.727630
                     Income Composition    0.721083
Infant Deaths        Population            0.671758
U-5 Deaths           Population            0.658680
Alcohol              Schooling             0.616975
Polio                Diphtheria            0.609245
dtype: float64 

Bottom 10 Correlated Features Pairs:
U-5 Deaths        Income Composition   -0.148097
Measles           BMI                  -0.153245
Infant Deaths     Polio                -0.156929
                  Diphtheria           -0.161871
Polio             Thinness 10-19       -0.164070
Life Expectancy   Infant Deaths        -0.169074
U-5 Deaths        Polio                -0.171164
Polio             Thinness 5-9         -0.174489
Adult Mortality   Alcohol              -0.175535
U-5 Deaths        Diphtheria           -0.178448
dtype: float64


columns=['Alcohol','BMI','Hep B','Measles','Polio','Diphtheria','HIVAIDS','Thinness 10-19',
         'Thinness 5-9','Adult Mortality','Infant Deaths','U-5 Deaths','Percent Expenditure'
         ,'Total Expenditure','Income Composition','Schooling']

for column,i in zip(columns,range(len(columns))):
    plt.subplot(4,4,i+1)
    sns.distplot(life_expectancy_data[column])  
    plt.tight_layout()
    sns.set(rc={'figure.figsize':(20,20)})


for column in life_expectancy_data.columns:
    if (column=='Country')or(column=='Status')or(column=='Life Expectancy ')or(column=='world')or(column=='Year'):
        pass
    else:
        LEfactorplot(column)
        sns.set(rc={'figure.figsize':(10,10)})
        sns.set(font_scale=1.5)
        plt.show()

C:\Users\HP\Anaconda3\lib\site-packages\ipykernel_launcher.py:7: RankWarning:

Polyfit may be poorly conditioned


data = life_expectancy_data.groupby('Year').median()


data


life_expectancy_data.copy()


df_2 = life_expectancy_data.copy()
df_2 = df_2[life_expectancy_data.Year == life_expectancy_data.Year.max()]
df_2.sort_values('Life expectancy ', ascending=False, inplace=True)
df_2


df_3 = life_expectancy_data.copy()
df_3 = df_3[(life_expectancy_data.Year == life_expectancy_data.Year.max()) | (life_expectancy_data.Year == 1900)]
df_3['pct_chg'] = life_expectancy_data['Life expectancy '].pct_change()*100
df_3


sns.pairplot(life_expectancy_data)

<seaborn.axisgrid.PairGrid at 0x2ab21fbea48>


df_4 = life_expectancy_data.copy()
df_4 = df_4.groupby('Year').std()
df_4.head()


count_test = life_expectancy_data['Status'].value_counts()
labels = life_expectancy_data['Status'].value_counts().index
plt.figure(figsize= (6,6))
plt.pie(count_test,labels=labels,autopct='%1.1f%%')
plt.legend(labels)
plt.show()


continents = {
    'NA':'North America',
    'SA':'South America',
    'AS':'Asia',
    'OC':'Australia',
    'AF':'Africa',
    'EU':'Europe'
    }


continent = []
for country in life_expectancy_data['Country']:
    try:
        continent.append(continents[(country_alpha2_to_continent_code(country_name_to_country_alpha2(country)))])
    except:
        continent.append("Africa")

life_expectancy_data["Continent"] = continent
to_buble = life_expectancy_data[["Country","Year","Life expectancy ","GDP","Population","Continent"]]
to_buble.dropna(inplace=True)


df = px.data.gapminder()
fig = px.scatter(to_buble, x = "GDP", y = "Life expectancy ", size = "Population", color = "Continent",
              hover_name = "Country", log_x = True, size_max = 50)
fig.show()


fig, ax = plt.subplots(figsize=(20,20)) 
sns.heatmap(life_expectancy_data.corr(), annot=True, ax=ax)
plt.show()


life_expectancy_data.isnull()


plt.subplots(figsize=(15,5))
life_expectancy_data['Continent'].value_counts(normalize = True)
life_expectancy_data['Continent'].value_counts(dropna = False).plot.bar(color=['black','orange','red','green','blue','grey'])
plt.title('Life Expectancy Under Each Continent Comparison')
plt.xlabel('Continents')
plt.ylabel('count')
plt.show()


life_expectancy_data['Continent'].value_counts()

Africa           976
Asia             704
Europe           610
North America    338
South America    160
Australia        150
Name: Continent, dtype: int64


plt.subplots(figsize = (15,5))
life_expectancy_data['Adult Mortality'].value_counts(normalize = True)
life_expectancy_data['Continent'].value_counts(dropna = False).plot.bar(figsize=(20,10),color=['black','orange','red','green','blue','grey'])
plt.title('Adult Mortality under each Country')
plt.xlabel('Continent')
plt.ylabel('Adult Mortality')
plt.show()


plt.subplots(figsize = (15,5))
life_expectancy_data['infant deaths'].value_counts(normalize = True)
life_expectancy_data['Continent'].value_counts(dropna = False).plot.bar(figsize=(20,10),color=['black','orange','red','green','blue','grey'])
plt.title('infant deaths under each Continent')
plt.xlabel('Continent')
plt.ylabel('infant deaths')
plt.show()


s = [
    life_expectancy_data['Life Expectancy '].dropna(),
    life_expectancy_data['Income composition of resources'].dropna(),
    life_expectancy_data['Schooling'].dropna()
]


for i in s:
    plt.figure(figsize = (20, 5))
    sns.distplot(i, kde=True, color='blue')


l = [
    life_expectancy_data['Life Expectancy '].dropna(),
    life_expectancy_data['Income composition of resources'].dropna(),
    life_expectancy_data['Schooling'].dropna()
]


for i in l:
    plt.figure(figsize = (20, 5))
    sns.distplot(i, kde=True, color='green')


life_expectancy_data['Schooling'].value_counts()

12.9    44
12.5    35
12.8    33
12.3    31
10.7    31
        ..
7.0      1
19.8     1
6.0      1
17.0     1
20.4     1
Name: Schooling, Length: 147, dtype: int64


# Converting Categorial values into Numerical values
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
labelencoder=LabelEncoder()
life_expectancy_data['Country']=labelencoder.fit_transform(life_expectancy_data['Country'])
life_expectancy_data['Year']=labelencoder.fit_transform(life_expectancy_data['Year'])
life_expectancy_data['Status']=labelencoder.fit_transform(life_expectancy_data['Status'])
life_expectancy_data.head()


nr_rows = 5
nr_cols = 4

fig, axs = plt.subplots(nr_rows,nr_cols, figsize = (nr_cols*5,nr_rows*5))
numerical_feats = life_expectancy_data.dtypes[life_expectancy_data.dtypes != "object"].index
li_num_feats = list(numerical_feats)
li_not_plot = []
li_plot_num_feats = [c for c in list(numerical_feats) if c not in li_not_plot]
life_expectancy_data.dropna(inplace = True)

for r in range(0, nr_rows):
    for c in range(0, nr_cols):
        i = r*nr_cols+c
        if i < len(li_plot_num_feats):
            sns.regplot(x = life_expectancy_data[li_plot_num_feats[i]], y = life_expectancy_data["Life expectancy "], color = 'green', ax = axs[r][c])
            stp = stats.pearsonr(life_expectancy_data[li_plot_num_feats[i]], life_expectancy_data["Life expectancy "])
            str_title = "r =" + "{0:.2f}".format(stp[0]) +"   ""p =" + "{0:.2f}".format(stp[1])
            axs[r][c].set_title(str_title, fontsize = 11)
            
plt.tight_layout()
sns.set(color_codes = True)
plt.show()


fig, axs = plt.subplots(2,3, figsize=(15,6), facecolor = 'w', edgecolor ='k')
fig.subplots_adjust(hspace = 0.5)

for conts, ax in zip(set(life_expectancy_data['Continent']), axs.flat):
    Conts = life_expectancy_data[life_expectancy_data['Continent'] == conts]
    sns.regplot(x = Conts['Alcohol'], y = Conts["Life expectancy "], color = 'blue', ax = ax).set_title(conts)
    
plt.tight_layout()
sns.set(color_codes = True)
plt.show()


sinakekelwe = life_expectancy_data["Life expectancy "]
features = life_expectancy_data[life_expectancy_data.columns.difference(["Life expectancy "])]
X_train,X_test, Y_train,Y_test = train_test_split(pd.get_dummies(features), sinakekelwe, test_size=0.3)


rf = RandomForestRegressor(random_state = 42)
print('Parameters currently in use:\n')
pprint(rf.get_params())

Parameters currently in use:

{'bootstrap': True,
 'criterion': 'mse',
 'max_depth': None,
 'max_features': 'auto',
 'max_leaf_nodes': None,
 'min_impurity_decrease': 0.0,
 'min_impurity_split': None,
 'min_samples_leaf': 1,
 'min_samples_split': 2,
 'min_weight_fraction_leaf': 0.0,
 'n_estimators': 'warn',
 'n_jobs': None,
 'oob_score': False,
 'random_state': 42,
 'verbose': 0,
 'warm_start': False}


n_estimators = [int(x) for x in np.linspace(start = 4, stop = 200, num = 10)]# Number of trees in random forest
max_features = ['auto','sqrt']# Number of features to consider at every split
max_depth = [int(x) for x in np.linspace(10,110, num = 11)]# Maximum number of levels in tree
max_depth.append(None)
min_samples_split = [2,5,10]# Minimum number of samples required to split a node
min_samples_leaf = [1,2,4]#Minimum number of samples required at each leaf node
bootstrap = [True,False]

# Creating the random grid
random_grid = { 
               'n_estimators': n_estimators,
               'max_features': max_features,
               'max_depth': max_depth,
               'min_samples_split': min_samples_split,
               'min_samples_leaf': min_samples_leaf,
               'bootstrap': bootstrap
}
pprint(random_grid)

{'bootstrap': [True, False],
 'max_depth': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, None],
 'max_features': ['auto', 'sqrt'],
 'min_samples_leaf': [1, 2, 4],
 'min_samples_split': [2, 5, 10],
 'n_estimators': [4, 25, 47, 69, 91, 112, 134, 156, 178, 200]}


rf_random= RandomizedSearchCV(estimator=rf,param_distributions=random_grid,n_iter=100,cv=5,verbose=2,random_state=42,n_jobs=-1)


rf_random

RandomizedSearchCV(cv=5, error_score='raise-deprecating',
                   estimator=RandomForestRegressor(bootstrap=True,
                                                   criterion='mse',
                                                   max_depth=None,
                                                   max_features='auto',
                                                   max_leaf_nodes=None,
                                                   min_impurity_decrease=0.0,
                                                   min_impurity_split=None,
                                                   min_samples_leaf=1,
                                                   min_samples_split=2,
                                                   min_weight_fraction_leaf=0.0,
                                                   n_estimators='warn',
                                                   n_jobs=None, oob_score=False,
                                                   random_sta...
                   iid='warn', n_iter=100, n_jobs=-1,
                   param_distributions={'bootstrap': [True, False],
                                        'max_depth': [10, 20, 30, 40, 50, 60,
                                                      70, 80, 90, 100, 110,
                                                      None],
                                        'max_features': ['auto', 'sqrt'],
                                        'min_samples_leaf': [1, 2, 4],
                                        'min_samples_split': [2, 5, 10],
                                        'n_estimators': [4, 25, 47, 69, 91, 112,
                                                         134, 156, 178, 200]},
                   pre_dispatch='2*n_jobs', random_state=42, refit=True,
                   return_train_score=False, scoring=None, verbose=2)


#rf_random.best_params_


def evaluate(model,test_features,test_labels):
    predictions = model.predict(test_features)
    errors = abs(predictions - test_labels)
    mape = 100 * np.mean(errors / test_labels)
    accuracy = 100 - mape
    print('Model Performance')
    print('Average Errors: {:0.4f} degrees.'.format(np.mean(errors)))
    print('Accuracy = {:0.2f}% .'.format(accuracy))
    
    return accuracy

base_model = RandomForestRegressor()
base_model.fit(X_test,Y_test)
base_accuracy = evaluate(base_model,X_test,Y_test)

best_random = rf_random.best_estimator_
random_accuracy = evaluate(best_random,X_test,Y_test)
print('Improvement of {:0.2f}%.'.format(100 *(random_accuracy - base_accuracy)/base_accuracy))

C:\Users\HP\Anaconda3\lib\site-packages\sklearn\ensemble\forest.py:245: FutureWarning:

The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.

Model Performance
Average Errors: 0.7009 degrees.
Accuracy = 98.96% .

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-148-462a4f31f270> in <module>
     14 base_accuracy = evaluate(base_model,X_test,Y_test)
     15 
---> 16 best_random = rf_random.best_estimator_
     17 random_accuracy = evaluate(best_random,X_test,Y_test)
     18 print('Improvement of {:0.2f}%.'.format(100 *(random_accuracy - base_accuracy)/base_accuracy))

AttributeError: 'RandomizedSearchCV' object has no attribute 'best_estimator_'


param_grid = { 
               'n_estimators': [10,30,100,120,150],
               'max_features': [2,3,4, 'auto','sqrt'],
               'max_depth': [10,20,50,None],
               'min_samples_split': [2,4,8],
               'min_samples_leaf': [1,3,5],
               'bootstrap': [True,False]
}
pprint(param_grid)

{'bootstrap': [True, False],
 'max_depth': [10, 20, 50, None],
 'max_features': [2, 3, 4, 'auto', 'sqrt'],
 'min_samples_leaf': [1, 3, 5],
 'min_samples_split': [2, 4, 8],
 'n_estimators': [10, 30, 100, 120, 150]}


rf = RandomForestRegressor()
grid_search = GridSearchCV(estimator = rf, param_grid = param_grid, cv = 3, n_jobs = -1, verbose = 2)


life_expectancy_data.fillna(0)


life_expectancy_data.dropna()


grid_search.fit(X_train, Y_train)

Fitting 3 folds for each of 1800 candidates, totalling 5400 fits

[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers.
[Parallel(n_jobs=-1)]: Done  33 tasks      | elapsed:    8.2s
[Parallel(n_jobs=-1)]: Done 154 tasks      | elapsed:   17.9s
[Parallel(n_jobs=-1)]: Done 357 tasks      | elapsed:   41.1s
[Parallel(n_jobs=-1)]: Done 640 tasks      | elapsed:  1.9min
[Parallel(n_jobs=-1)]: Done 1005 tasks      | elapsed:  2.6min
[Parallel(n_jobs=-1)]: Done 1450 tasks      | elapsed:  4.2min
[Parallel(n_jobs=-1)]: Done 1977 tasks      | elapsed:  6.0min
[Parallel(n_jobs=-1)]: Done 2584 tasks      | elapsed:  7.9min
[Parallel(n_jobs=-1)]: Done 3273 tasks      | elapsed: 10.6min
[Parallel(n_jobs=-1)]: Done 4042 tasks      | elapsed: 14.7min
[Parallel(n_jobs=-1)]: Done 4893 tasks      | elapsed: 18.7min
[Parallel(n_jobs=-1)]: Done 5400 out of 5400 | elapsed: 21.4min finished

GridSearchCV(cv=3, error_score='raise-deprecating',
             estimator=RandomForestRegressor(bootstrap=True, criterion='mse',
                                             max_depth=None,
                                             max_features='auto',
                                             max_leaf_nodes=None,
                                             min_impurity_decrease=0.0,
                                             min_impurity_split=None,
                                             min_samples_leaf=1,
                                             min_samples_split=2,
                                             min_weight_fraction_leaf=0.0,
                                             n_estimators='warn', n_jobs=None,
                                             oob_score=False, random_state=None,
                                             verbose=0, warm_start=False),
             iid='warn', n_jobs=-1,
             param_grid={'bootstrap': [True, False],
                         'max_depth': [10, 20, 50, None],
                         'max_features': [2, 3, 4, 'auto', 'sqrt'],
                         'min_samples_leaf': [1, 3, 5],
                         'min_samples_split': [2, 4, 8],
                         'n_estimators': [10, 30, 100, 120, 150]},
             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
             scoring=None, verbose=2)


print(grid_search.best_params_)
best_grid = grid_search.best_estimator_
grid_accuracy = evaluate(best_grid,X_test,Y_test)
print('Improvement of {:0.2f}%.'.format(100 *(grid_accuracy - base_accuracy)/base_accuracy))

{'bootstrap': False, 'max_depth': 50, 'max_features': 'sqrt', 'min_samples_leaf': 1, 'min_samples_split': 2, 'n_estimators': 150}
Model Performance
Average Errors: 1.0564 degrees.
Accuracy = 98.44% .
Improvement of -0.53%.


model_predictions = best_grid.predict(X_test)
residuals = model_predictions - Y_test


plt.figure(figsize=(20,5))
sns.distplot(residuals, kde=True, color='brown')
plt.title('Residual Graph Plot')
plt.xlabel('Residuals (Predictions - Actual)')
plt.ylabel('Density')
plt.show()


print("R-squared Score obtained for Predicting Life Expectancy is {0}".format(r2_score(Y_test,model_predictions)))

R-squared Score obtained for Predicting Life Expectancy is 0.9649812919075508


# Put models in a dictionary
models = { "Linear Regression": LinearRegression(), 
           "Random Forest": RandomForestRegressor(),
           "Decision tree": DecisionTreeRegressor()}

# Create function to fit and score models
def fit_and_score(models, X_train, X_test, Y_train, Y_test):
    """
    Fits and evaluates given machine learning models.
    models : a dict of different Scikit-Learn machine learning models
    X_train : training data
    X_test : testing data
    Y_train : labels assosciated with training data
    Y_test : labels assosciated with test data
    """
    # Random seed for reproducible results
    np.random.seed(101)
    # Make a list to keep model scores
    model_scores = {}
    # Loop through models
    for name, model in models.items():
        model.fit(X_train, Y_train)
        model_scores[name] = model.score(X_test, Y_test)
    return model_scores


# Evaluate the Model Scores
model_scores = fit_and_score(models=models,
                             X_train=X_train,
                             X_test=X_test,
                             Y_train=Y_train,
                             Y_test=Y_test)
model_scores

C:\Users\HP\Anaconda3\lib\site-packages\sklearn\ensemble\forest.py:245: FutureWarning:

The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.

{'Linear Regression': 0.8269515213246902,
 'Random Forest': 0.9543157752594978,
 'Decision tree': 0.9150919470011675}


model_compare = pd.DataFrame(model_scores, index=['score'])
model_compare.T.plot.bar();


# Different RandomForestRegressor hyperparameters
rf_grid = {"n_estimators": np.arange(10, 100, 10),
           "max_depth": [None, 3, 5, 10],
           "min_samples_split": np.arange(2, 20, 2),
           "min_samples_leaf": np.arange(1, 20, 2),
           "max_features": [0.5, 1, "sqrt", "auto"],
           }

# Instantiate RandomizedSearchCV model
rs_model = RandomizedSearchCV(RandomForestRegressor(n_jobs=-1,
                              random_state=42),
                              param_distributions=rf_grid,
                              n_iter=20,
                              cv=5,
                              verbose=True)

# Fit the RandomizedSearchCV model
rs_model.fit(X_train, Y_train)

Fitting 5 folds for each of 20 candidates, totalling 100 fits

[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done 100 out of 100 | elapsed:   34.8s finished

RandomizedSearchCV(cv=5, error_score='raise-deprecating',
                   estimator=RandomForestRegressor(bootstrap=True,
                                                   criterion='mse',
                                                   max_depth=None,
                                                   max_features='auto',
                                                   max_leaf_nodes=None,
                                                   min_impurity_decrease=0.0,
                                                   min_impurity_split=None,
                                                   min_samples_leaf=1,
                                                   min_samples_split=2,
                                                   min_weight_fraction_leaf=0.0,
                                                   n_estimators='warn',
                                                   n_jobs=-1, oob_score=False,
                                                   random_state...
                   iid='warn', n_iter=20, n_jobs=None,
                   param_distributions={'max_depth': [None, 3, 5, 10],
                                        'max_features': [0.5, 1, 'sqrt',
                                                         'auto'],
                                        'min_samples_leaf': array([ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19]),
                                        'min_samples_split': array([ 2,  4,  6,  8, 10, 12, 14, 16, 18]),
                                        'n_estimators': array([10, 20, 30, 40, 50, 60, 70, 80, 90])},
                   pre_dispatch='2*n_jobs', random_state=None, refit=True,
                   return_train_score=False, scoring=None, verbose=True)


# Most ideal hyperparamters
ideal_model = RandomForestRegressor(n_estimators=30,
                                    min_samples_split=2,
                                    min_samples_leaf=1,
                                    max_features=0.5,
                                    max_depth=10,
                                    n_jobs=-1,
                                    random_state=101)

# Fit the ideal model
ideal_model.fit(X_train, Y_train)

RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=10,
                      max_features=0.5, max_leaf_nodes=None,
                      min_impurity_decrease=0.0, min_impurity_split=None,
                      min_samples_leaf=1, min_samples_split=2,
                      min_weight_fraction_leaf=0.0, n_estimators=30, n_jobs=-1,
                      oob_score=False, random_state=101, verbose=0,
                      warm_start=False)


ideal_model.score(X_test, Y_test)

0.9564611894892975


# Make predictions on test data
y_preds=ideal_model.predict(X_test)
y_preds

array([63.86528661, 82.55902899, 66.5189774 , 52.95046188, 63.56031896,
       83.38065438, 72.91785092, 64.2427185 , 79.71590462, 78.57298335,
       52.21741297, 74.31241713, 74.19732853, 67.25544869, 69.93766859,
       63.46219794, 72.50650492, 56.55138511, 62.57370103, 63.65615174,
       69.64670402, 58.29669444, 62.07615505, 78.28981575, 70.42678249,
       83.45626916, 70.50852181, 72.31069105, 81.03701328, 67.7187892 ,
       79.92449871, 69.426096  , 68.50335615, 68.69907611, 68.59248371,
       74.63332166, 72.11771098, 74.52979998, 65.29040075, 69.45776389,
       61.42402644, 81.06133293, 49.09482949, 73.58069444, 69.6058663 ,
       65.48061715, 82.49686713, 73.02938832, 67.28727443, 54.05196941,
       79.09204428, 73.77880163, 67.47625522, 73.52014064, 69.10189638,
       64.82736495, 70.42463076, 50.27159107, 74.37627742, 79.61049001,
       64.18040734, 73.85653821, 74.31872496, 80.36174507, 48.14805964,
       66.42418803, 55.87649671, 47.92938889, 52.3267159 , 68.40077296,
       79.68390692, 72.38049163, 78.63320329, 78.78726693, 74.06645336,
       76.17722816, 58.5023826 , 56.07728895, 81.26796086, 74.24112325,
       68.21336171, 66.74119732, 63.33418119, 72.80531308, 74.50258637,
       68.36979134, 53.91632381, 67.1655151 , 58.81494634, 73.84011615,
       68.6476461 , 77.3326513 , 83.03899284, 72.20680543, 70.75451242,
       76.19543057, 75.08764527, 55.059726  , 77.7169762 , 78.48638503,
       64.29155166, 58.4217171 , 69.09767351, 57.20667733, 60.74509937,
       73.04638706, 75.6672095 , 65.76646347, 71.22519242, 67.12050247,
       57.57029529, 69.90981286, 69.25909963, 73.46613517, 57.0962755 ,
       72.17193972, 82.24251848, 82.24805223, 72.65154325, 69.05932723,
       48.27467251, 68.48164221, 78.03949146, 73.78191374, 62.14048155,
       74.15616366, 80.8403603 , 82.17281425, 73.02101938, 74.16468078,
       80.2729902 , 73.36730049, 71.99737165, 57.23658441, 60.0915555 ,
       64.57021702, 55.24405423, 76.41815365, 72.45303453, 59.96910999,
       80.77597978, 65.23041549, 75.02321703, 81.7487576 , 69.34862828,
       83.1689086 , 72.5138843 , 76.25262485, 63.56292913, 62.83424907,
       76.79354892, 63.81851947, 67.07064842, 73.53983222, 68.09055982,
       78.3369098 , 74.03114109, 70.71125674, 80.30873718, 71.31907789,
       50.08633788, 73.89059983, 56.57184953, 53.28339813, 71.72890382,
       77.75795805, 80.17863714, 74.1746947 , 72.91788976, 76.22465357,
       71.28927402, 49.24128328, 74.15030245, 63.75463049, 82.01811199,
       73.54351184, 81.97157408, 59.28445334, 72.83963449, 66.94901658,
       69.14501452, 66.16816219, 58.33912584, 45.46568376, 64.84912542,
       78.63340443, 81.34814177, 60.58538913, 72.15168109, 72.02384607,
       71.43908561, 64.76643462, 69.88226836, 69.04526758, 72.86613867,
       70.67344135, 54.22798   , 76.73687256, 74.14915317, 75.79209155,
       82.81082931, 80.1204837 , 73.67821515, 74.48632248, 74.13440187,
       82.03940176, 83.15651072, 55.1982392 , 45.35224858, 73.29374488,
       73.12783072, 74.78286312, 64.23949865, 74.29032004, 49.89553172,
       74.34349149, 66.93519174, 78.58306648, 74.49125116, 75.70373325,
       73.39606725, 53.58962133, 74.41172607, 73.25657372, 76.59674659,
       73.19041895, 82.80355385, 72.94783594, 81.23457174, 72.83007918,
       65.31221447, 72.41875832, 69.55124903, 80.61913976, 65.05172288,
       62.23621458, 52.69456079, 82.73688204, 62.63475415, 78.26959491,
       75.68323156, 74.09494884, 76.26457721, 53.97596355, 62.42684396,
       60.01973294, 65.7703606 , 59.8366259 , 83.11931548, 71.18050091,
       83.28404638, 73.19335315, 51.78480718, 72.71118902, 54.22265933,
       79.94113402, 82.26492434, 71.80111419, 73.31307371, 78.18010767,
       82.20719822, 59.62230284, 82.21282624, 58.84971154, 69.90543616,
       73.95239667, 79.52893198, 61.37672294, 48.23913889, 82.64489122,
       51.36682672, 63.48454226, 58.83673953, 82.05359005, 74.82859243,
       75.3108072 , 60.17920043, 79.26792029, 78.32784547, 62.17684921,
       59.7894755 , 61.76277055, 73.625304  , 75.83345893, 59.91828375,
       79.11459461, 49.69351656, 75.19498017, 82.43742041, 55.69720138,
       83.48619267, 73.84777246, 60.44829954, 73.61835531, 82.06181358,
       55.72590067, 73.52267634, 72.90911881, 76.87128552, 65.29252525,
       75.68474422, 72.94830116, 75.23057245, 82.68192975, 70.52884565,
       61.50321138, 72.02043445, 58.24087304, 67.89021458, 81.29211137,
       68.5981536 , 73.13396567, 82.81276392, 65.61545098, 76.5017874 ,
       73.53392485, 71.27406705, 81.33042495, 58.62212178, 74.19446127,
       74.52327685, 58.86312583, 64.05364923, 81.2538182 , 68.58255159,
       52.24393155, 57.40979022, 62.20771775, 62.44412999, 48.72246125,
       75.04059811, 71.56883708, 69.6958574 , 55.08279647, 69.22917319,
       54.43887843, 73.51889802, 66.1911421 , 63.76501233, 72.97735991,
       58.44769893, 51.7504924 , 65.79147054, 56.8511524 , 67.89369032,
       71.42455219, 54.83306168, 81.75058301, 66.0333547 , 62.44567284,
       57.81104765, 70.99353563, 54.74277135, 75.27695131, 55.07963786,
       56.46591095, 67.48936725, 78.13861987, 74.75914962, 68.85484107,
       81.4982862 , 72.02851826, 72.85683013, 74.55297788, 66.72466853,
       73.36929808, 53.90703001, 68.63015992, 67.85198711, 48.3386152 ,
       75.88118866, 76.3626219 , 62.87853826, 66.91599179, 73.44357322,
       68.47581398, 74.30866114, 80.70808921, 70.62587191, 74.51090328,
       73.31278071, 78.86670655, 74.06068889, 75.81753057, 74.53425972,
       71.75233045, 73.90319254, 78.91881614, 78.99101981, 75.35680342,
       63.86385739, 77.41422785, 82.21892249, 75.41030269, 70.2273357 ,
       78.11469477, 72.74372585, 51.10859666, 52.61172677, 74.75417081,
       65.05006038, 81.69379363, 56.09797953, 75.04457123, 59.35727171,
       72.56977404, 79.93071979, 60.20056928, 71.5840507 , 70.88629288,
       73.86173016, 64.48184756, 63.42499264, 72.59418194, 62.72702841,
       72.05905815, 79.58604092, 82.28267547, 58.19612712, 75.56466514,
       77.62705363, 75.3466347 , 48.66019934, 71.07471717, 73.94967184,
       74.1178702 , 71.72050903, 58.8236344 , 64.93975902, 74.94165193,
       72.97231341, 75.85362427, 74.92830145, 58.95626826, 79.4252786 ,
       74.40550732, 71.40905214, 56.7701176 , 64.94287387, 66.10178886,
       54.03924295, 61.14465608, 69.56815805, 73.25217744, 75.01982926,
       72.53814498, 75.78843153, 63.39508847, 73.89609232, 78.82378081,
       70.68800346, 73.28017634, 52.7373564 , 79.837468  , 72.89986912,
       53.15731071, 64.21764547, 80.74932399, 76.53963349, 70.60829173,
       73.12793634, 73.9491744 , 71.9212788 , 81.85884698, 53.61489422,
       66.95334375, 74.91149267, 73.95549427, 74.25444495, 73.51703757,
       65.54596127, 57.56353789, 72.40650947, 74.31926281, 75.60014885,
       82.02625904, 79.2594773 , 72.46614481, 71.91811086, 75.42660783,
       74.87374016, 77.02013424, 63.00610678, 74.33623645, 74.56491599,
       75.68936541, 66.83888618, 78.43852154, 69.28881337, 58.00750638,
       73.24944616, 75.01688672, 63.70664023, 77.27096107, 65.31674658,
       59.49800373, 70.09149627, 73.1547186 , 75.51509115, 78.88217016,
       78.36246969, 72.42227328, 47.35024423, 51.73470593, 53.16580345,
       82.29298685, 52.43804136, 74.52793171, 76.83889148, 74.59603495,
       76.06930835, 81.3236062 , 69.55381275, 71.04814191, 53.55631629,
       65.32217417, 67.93428341, 66.12603506, 76.20711973, 57.07726635,
       50.58877793, 67.97505757, 72.67545673, 69.37938395, 63.40746414,
       70.05631717, 73.19683698, 84.12774186, 73.8380671 , 75.49705093,
       83.49272122, 56.54791172, 73.2660622 , 65.8122888 , 67.14273452,
       73.51487026, 51.27153502, 70.77515088, 63.15733491, 63.86879536,
       53.95554688, 82.09466522, 73.07223284, 56.77626367, 78.90050723,
       74.33653612, 68.23702027, 72.90374594, 51.64494063, 80.91317481,
       58.79602617, 81.25611814, 74.81091385, 52.24320561, 75.13605318,
       74.61689056, 62.25569907, 65.48266467, 81.01187217, 71.00176058,
       46.31714286, 69.09096531, 74.77378877, 53.89211639, 55.38753352,
       74.00374711, 59.65454487, 82.11090327, 75.37993327, 74.93149582,
       71.97125195, 61.45878631, 80.49709614, 58.26055671, 61.89059385,
       71.82581334, 57.73089664, 65.01760418, 79.12915667, 68.94038565,
       75.07328233, 69.24765453, 71.30584076, 73.48893146, 72.13263292,
       72.40989987, 54.41152413, 66.08635274, 73.80870006, 72.68507422,
       67.48152185, 76.46018026, 72.60344272, 52.16359493, 81.92908852,
       67.74399789, 61.22050256, 70.26175159, 74.53397335, 57.81881511,
       74.04956539, 47.27900794, 73.13471726, 67.46721566, 63.39033569,
       71.9098058 , 53.51630009, 81.38237261, 83.34038515, 71.45373482,
       79.47851378, 53.93100244, 75.29997943, 70.3293439 , 66.52868045,
       63.62787261, 76.04055089, 76.05276865, 55.92347749, 63.77082731,
       72.78653678, 65.58336986, 67.04722353, 67.65278749, 49.55157584,
       51.32731479, 80.63753218, 54.40945262, 79.55585066, 68.32844532,
       69.55718208, 74.72985034, 69.53991231, 59.89568251, 53.14573026,
       62.61596659, 82.36007055, 72.6460991 , 60.80499418, 81.03149766,
       72.01534607, 69.82303633, 73.254661  , 73.88886006, 72.92761142,
       72.21262864, 69.16428206, 72.15031173, 75.42199729, 72.88427433,
       69.2964651 , 73.44373037, 82.50606321, 73.08236824, 67.13598912,
       57.00270678, 70.57534279, 76.95769592, 67.63321215, 73.2632929 ,
       74.73832418, 78.24643563, 73.51910347, 82.20351111, 55.52486581,
       58.01039466, 63.92905224, 78.83940271, 75.47849623, 62.45890945,
       72.57681064, 73.14168374, 77.41320423, 79.05207477, 72.19482735,
       78.09389245, 79.98314759, 68.51544384, 62.77161111, 53.12751022,
       70.43610865, 61.9343416 , 74.30409665, 72.67054724, 52.25940296,
       44.90314815, 69.7306617 , 77.7802328 , 72.42927813, 73.56616566,
       74.69587332, 64.45305302, 73.32463747, 72.23950256, 61.26385255,
       68.987959  , 63.19603194, 56.17037549, 82.40976529, 74.22611503,
       69.10553542, 52.22987034, 69.61486188, 74.77141944, 72.85965841,
       57.81846159, 75.99500072, 72.47860903, 71.79399987, 82.38155077,
       52.78371512, 71.39164366, 72.37687659, 74.16271782, 71.26263792,
       59.68522166, 74.79321065, 73.03097291, 61.92752047, 69.52055721,
       71.9070972 , 72.74887752, 74.92260633, 81.08598442, 76.38894754,
       72.19423873, 62.60726518, 81.87575174, 83.32167964, 62.97391216,
       73.38079181, 70.7418249 , 73.58834431, 52.33152139, 66.5606164 ,
       79.93881127, 74.91809939, 68.32479093, 71.77173711, 72.8457657 ,
       83.04810786, 72.53174684, 73.55526161, 80.12236025, 72.24875467,
       73.24088523, 72.22047408, 82.11532595, 72.54847316, 74.69798821,
       73.24618506, 72.46891595, 70.33636941, 74.29860162, 72.55368498,
       66.9081489 , 72.54579773, 50.01613831, 67.31993054, 75.62316805,
       83.3650054 , 79.05769041, 70.71908302, 74.26113208, 56.81010656,
       71.69132268, 53.23421836, 61.55653765, 78.32162101, 52.071745  ,
       82.73688204, 59.6849082 , 65.51874934, 82.11386075, 75.02388941,
       81.2466116 , 73.56738701, 63.60318404, 75.06219069, 73.53748155,
       81.80450926, 65.40079882, 76.07536051, 69.86747016, 83.01113148,
       82.70045558, 73.76884897, 68.0441324 , 59.30879038, 59.82002577,
       58.74828558, 60.2239086 , 51.17293553, 74.75407529, 62.73456492,
       73.93581469, 51.2388613 , 76.56155998, 76.40112415, 68.01317585,
       67.97763659, 72.65256844, 75.40570374, 63.19905075, 80.62904092,
       65.46335096, 47.4687383 , 77.42962261, 61.55892099, 61.20401969,
       52.41618457, 72.46627393, 78.70332141, 72.02101922, 55.18399558,
       45.37762821, 82.11188518, 53.9380659 , 57.27411751, 68.52144265,
       82.50210985, 73.5196423 , 76.24706236, 72.01082054, 72.87394529,
       74.43047656, 76.75242042, 73.20192088, 79.63386218, 55.5789477 ,
       51.92340592, 62.80029352, 72.35162427, 80.67219163, 80.2480589 ,
       54.91054957, 72.71191024, 71.90499881, 53.08601439, 72.86430365,
       48.25032604, 65.91328917, 76.21884296, 69.57256892, 80.27337941,
       81.65422483, 68.95866573, 73.96850636, 60.70336869, 78.40726079,
       67.95746573, 55.56107   , 49.97574074, 72.80790991, 71.6686517 ,
       74.96797082, 49.63952557, 74.30100047, 62.67767272, 79.13368465,
       73.71547036, 53.12496517, 74.97632627, 73.19736896, 52.85980531,
       82.52140857, 76.29597755, 73.12441135, 82.21220074, 81.69537924,
       73.06550757, 73.38142713, 69.69873939, 51.82403502, 62.49428686,
       73.1082864 , 62.23018545, 74.48354994, 74.58458   , 75.86674672,
       49.27547884, 80.32790402])


Y_test

1198    63.7
1252    81.0
947     65.5
2419    51.9
1730    63.2
        ... 
2049    75.0
982     73.9
2754    75.6
2498    47.8
547     79.9
Name: Life expectancy , Length: 882, dtype: float64


print("Mean squared error: %.2f"% mean_squared_error(Y_test, y_preds))
print("Mean absolute error: %.2f"% mean_absolute_error(Y_test, y_preds))
print('R_square score: %.2f' % r2_score(Y_test, y_preds))

Mean squared error: 3.83
Mean absolute error: 1.29
R_square score: 0.96


# Find feature importance of our best model
ideal_model.feature_importances_

array([1.95808273e-02, 3.49787228e-01, 7.92179866e-03, 1.34516090e-02,
       2.37924027e-01, 7.22086557e-03, 3.97111922e-03, 1.79755495e-02,
       3.28102304e-03, 1.91615207e-03, 2.05836814e-01, 2.26108485e-03,
       1.54352835e-02, 3.19983554e-03, 5.04290712e-02, 6.98014812e-03,
       5.20187754e-03, 6.15440189e-03, 7.03596991e-03, 4.68758398e-03,
       1.34829108e-02, 1.25167912e-02, 5.57771211e-04, 7.75785022e-04,
       3.00375014e-04, 2.02176934e-03, 9.23270644e-05])


# Function for plotting feature importance
def plot_features(columns, importances):
    df = (pd.DataFrame({"features": columns,
                        "feature_importances": importances})
          .sort_values("feature_importances", ascending=False)
          .reset_index(drop=True))
    
    # Plot the dataframe
    fig, ax = plt.subplots()
    ax.barh(df["features"], df["feature_importances"])
    ax.set_ylabel("Features")
    ax.set_xlabel("Feature importance")
    ax.invert_yaxis()


plot_features(X_train.columns, ideal_model.feature_importances_)


X_train, X_test, Y_train, Y_test = model_selection.train_test_split(life_expectancy_data, y, test_size=0.2, random_state=42)
x_valid, X_test, y_valid, Y_test = model_selection.train_test_split(X_test, Y_test, test_size=0.5, random_state=42)
print(f'X_train shape -->{X_train.shape}')
print(f'X_valid shape -->{x_valid.shape}')
print(f'X_test shape -->{X_test.shape}')
print(f'y_train shape -->{Y_train.shape}')
print(f'y_valid shape -->{y_valid.shape}')
print(f'y_test shape -->{Y_test.shape}')

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-177-aa42f0b1e48b> in <module>
----> 1 X_train, X_test, Y_train, Y_test = model_selection.train_test_split(life_expectancy_data, y, test_size=0.2, random_state=42)
      2 x_valid, X_test, y_valid, Y_test = model_selection.train_test_split(X_test, Y_test, test_size=0.5, random_state=42)
      3 print(f'X_train shape -->{X_train.shape}')
      4 print(f'X_valid shape -->{x_valid.shape}')
      5 print(f'X_test shape -->{X_test.shape}')

NameError: name 'model_selection' is not defined

	Year	Life Expectancy	Adult Mortality	Infant Deaths	Alcohol	Percent Expenditure	Hep B	Measles	BMI	U-5 Deaths	Polio	Total Expenditure	Diphtheria	HIVAIDS	GDP	Population	Thinness 10-19	Thinness 5-9	Income Composition	Schooling
count	2938.000000	2928.000000	2928.000000	2938.000000	2744.000000	2938.000000	2385.000000	2938.000000	2904.000000	2938.000000	2919.000000	2712.00000	2919.000000	2938.000000	2490.000000	2.286000e+03	2904.000000	2904.000000	2771.000000	2775.000000
mean	2007.518720	69.224932	164.796448	30.303948	4.602861	738.251295	80.940461	2419.592240	38.321247	42.035739	82.550188	5.93819	82.324084	1.742103	7483.158469	1.275338e+07	4.839704	4.870317	0.627551	11.992793
std	4.613841	9.523867	124.292079	117.926501	4.052413	1987.914858	25.070016	11467.272489	20.044034	160.445548	23.428046	2.49832	23.716912	5.077785	14270.169342	6.101210e+07	4.420195	4.508882	0.210904	3.358920
min	2000.000000	36.300000	1.000000	0.000000	0.010000	0.000000	1.000000	0.000000	1.000000	0.000000	3.000000	0.37000	2.000000	0.100000	1.681350	3.400000e+01	0.100000	0.100000	0.000000	0.000000
25%	2004.000000	63.100000	74.000000	0.000000	0.877500	4.685343	77.000000	0.000000	19.300000	0.000000	78.000000	4.26000	78.000000	0.100000	463.935626	1.957932e+05	1.600000	1.500000	0.493000	10.100000
50%	2008.000000	72.100000	144.000000	3.000000	3.755000	64.912906	92.000000	17.000000	43.500000	4.000000	93.000000	5.75500	93.000000	0.100000	1766.947595	1.386542e+06	3.300000	3.300000	0.677000	12.300000
75%	2012.000000	75.700000	228.000000	22.000000	7.702500	441.534144	97.000000	360.250000	56.200000	28.000000	97.000000	7.49250	97.000000	0.800000	5910.806335	7.420359e+06	7.200000	7.200000	0.779000	14.300000
max	2015.000000	89.000000	723.000000	1800.000000	17.870000	19479.911610	99.000000	212183.000000	87.300000	2500.000000	99.000000	17.60000	99.000000	50.600000	119172.741800	1.293859e+09	27.700000	28.600000	0.948000	20.700000

	Country	Year	Status	Life Expectancy	Adult Mortality	Infant Deaths	Alcohol	Percent Expenditure	Hep B	Measles	BMI	U-5 Deaths	Polio	Total Expenditure	Diphtheria	HIVAIDS	GDP	Population	Thinness 10-19	Thinness 5-9	Income Composition	Schooling
count	2938	2938.000000	2938	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2938.000000	2.938000e+03	2938.000000	2938.000000	2938.000000	2938.000000
unique	193	NaN	2	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
top	Afghanistan	NaN	Developing	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
freq	16	NaN	2426	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
mean	NaN	2007.518720	NaN	69.224932	164.796448	30.303948	4.602861	738.251295	80.940461	2419.592240	38.321247	42.035739	82.550188	5.938190	82.324084	1.742103	7483.158469	1.275338e+07	4.839704	4.870317	0.627551	11.992793
std	NaN	4.613841	NaN	9.507640	124.080302	117.926501	3.916288	1987.914858	22.586855	11467.272489	19.927677	160.445548	23.352143	2.400274	23.640073	5.077785	13136.800417	5.381546e+07	4.394535	4.482708	0.204820	3.264381
min	NaN	2000.000000	NaN	36.300000	1.000000	0.000000	0.010000	0.000000	1.000000	0.000000	1.000000	0.000000	3.000000	0.370000	2.000000	0.100000	1.681350	3.400000e+01	0.100000	0.100000	0.000000	0.000000
25%	NaN	2004.000000	NaN	63.200000	74.000000	0.000000	1.092500	4.685343	80.940461	0.000000	19.400000	0.000000	78.000000	4.370000	78.000000	0.100000	580.486996	4.189172e+05	1.600000	1.600000	0.504250	10.300000
50%	NaN	2008.000000	NaN	72.000000	144.000000	3.000000	4.160000	64.912906	87.000000	17.000000	43.000000	4.000000	93.000000	5.938190	93.000000	0.100000	3116.561755	3.675929e+06	3.400000	3.400000	0.662000	12.100000
75%	NaN	2012.000000	NaN	75.600000	227.000000	22.000000	7.390000	441.534144	96.000000	360.250000	56.100000	28.000000	97.000000	7.330000	97.000000	0.800000	7483.158469	1.275338e+07	7.100000	7.200000	0.772000	14.100000
max	NaN	2015.000000	NaN	89.000000	723.000000	1800.000000	17.870000	19479.911610	99.000000	212183.000000	87.300000	2500.000000	99.000000	17.600000	99.000000	50.600000	119172.741800	1.293859e+09	27.700000	28.600000	0.948000	20.700000

	Country	Year	Status	Life Expectancy	Adult Mortality	Infant Deaths	Alcohol	Percent Expenditure	Hep B	Measles	BMI	U-5 Deaths	Polio	Total Expenditure	Diphtheria	HIVAIDS	GDP	Population	Thinness 10-19	Thinness 5-9	Income Composition	Schooling
2489	Swaziland	2015	Developing	58.9	373.0	2	4.602861	0.000000	9.0	0	32.3	3	84.0	5.93819	9.0	7.1	3136.925110	0.131911	4.0	4.1	0.541	11.4
2490	Swaziland	2014	Developing	58.4	382.0	2	0.010000	574.389510	98.0	0	31.8	3	98.0	9.25000	98.0	7.3	3464.351690	0.129597	4.3	4.3	0.541	11.4
2491	Swaziland	2013	Developing	57.6	393.0	2	0.010000	708.955665	98.0	0	31.2	3	98.0	9.66000	98.0	9.8	3598.759720	1.271456	4.5	4.6	0.539	11.4
2492	Swaziland	2012	Developing	56.5	412.0	2	0.010000	720.233393	95.0	0	3.7	3	92.0	8.76000	95.0	12.2	3851.515470	1.248158	4.8	4.9	0.534	11.3
2493	Swaziland	2011	Developing	55.0	438.0	2	5.200000	735.709098	91.0	0	3.2	3	85.0	8.61000	91.0	15.7	3934.273250	1.225258	5.1	5.2	0.526	11.2
2494	Swaziland	2010	Developing	53.6	459.0	2	4.930000	56.936706	89.0	313	29.7	4	89.0	8.47000	89.0	21.6	369.239336	0.122843	5.4	5.6	0.523	11.0
2495	Swaziland	2009	Developing	52.6	46.0	3	4.900000	47.616452	88.0	26	29.3	4	89.0	8.46000	88.0	33.7	332.517125	0.118675	5.8	5.9	0.519	10.8
2496	Swaziland	2008	Developing	51.4	477.0	3	4.870000	413.006303	9.0	1	28.9	4	89.0	8.19000	88.0	40.2	2842.438422	1.158897	6.1	6.3	0.514	10.6
2497	Swaziland	2007	Developing	50.0	51.0	3	5.550000	43.366500	92.0	0	28.5	4	88.0	7.50000	87.0	40.7	347.487980	1.138434	6.5	6.7	0.508	10.5
2498	Swaziland	2006	Developing	47.8	564.0	3	5.530000	437.080244	93.0	0	28.2	4	88.0	6.81000	87.0	43.7	2937.367230	0.112514	6.9	7.1	0.502	9.9
2499	Swaziland	2005	Developing	46.0	63.0	3	5.080000	372.165147	95.0	0	27.8	4	88.0	6.80000	86.0	49.1	2873.862141	0.115873	7.3	7.5	0.495	9.7
2500	Swaziland	2004	Developing	45.6	69.0	3	5.780000	37.438577	93.0	0	27.4	4	88.0	5.88000	86.0	50.3	2529.633557	0.019553	7.7	7.9	0.492	9.4
2501	Swaziland	2003	Developing	45.9	6.0	3	5.650000	2.819124	9.0	350	27.1	4	87.0	5.71000	85.0	50.6	22.994490	0.187392	8.2	8.4	0.493	9.1
2502	Swaziland	2002	Developing	46.4	587.0	3	5.520000	131.042127	88.0	37	26.7	4	87.0	5.16000	85.0	49.9	1324.996228	0.001893	8.6	8.8	0.502	9.2
2503	Swaziland	2001	Developing	47.1	568.0	3	6.720000	143.619732	86.0	49	26.3	4	87.0	5.11000	84.0	48.8	1437.634951	0.172927	9.0	9.2	0.506	9.3
2504	Swaziland	2000	Developing	48.4	536.0	3	7.190000	25.216833	83.0	10	25.9	4	87.0	5.26000	84.0	46.4	1637.456700	0.161468	9.4	9.6	0.516	9.4

	Country	Life Expectancy
84	Japan	82.53750
165	Sweden	82.51875
75	Iceland	82.44375
166	Switzerland	82.33125
60	France	82.21875
82	Italy	82.18750
160	Spain	82.06875
7	Australia	81.81250
125	Norway	81.79375
30	Canada	81.68750

	Country	Life Expectancy
152	Sierra Leone	46.11250
31	Central African Republic	48.51250
94	Lesotho	48.78125
3	Angola	49.01875
100	Malawi	49.89375
32	Chad	50.38750
44	Côte d'Ivoire	50.38750
192	Zimbabwe	50.48750
164	Swaziland	51.32500
123	Nigeria	51.35625

Imports & Settings¶

Basic Data Information¶

Variables¶

DATA VISUALIZATION¶

How has the median life expectancy for all countries changed over time?¶

What are the current life expectancies for each country?¶

What are the growth rates in life expectancy for each country since 1900?¶

How has the standard deviation of life expectancy changed over time?¶

How many countries had decreasing life expectancies per year?¶

Life Expectancy has a dense distribution between 70 -76 years¶

Checking the impact of Alcohol consumption over Life expectancy for all the different continents¶

Life expectancy Estimation or Prediction Regression Model¶

Random Search Cross Validation¶

Hyerparameter tuning with RandomizedSearchCV¶

Evaluating the Model¶

Feature Importance¶

	Country	Year	Status	Life Expectancy	Adult Mortality	Infant Deaths	Alcohol	Percent Expenditure	Hep B	Measles	BMI	U-5 Deaths	Polio	Total Expenditure	Diphtheria	HIVAIDS	GDP	Population	Thinness 10-19	Thinness 5-9	Income Composition	Schooling
1127	Haiti	2010	Developing	36.3	682.0	23	5.76	36.292918	80.940461	0	44.2	58	66.0	8.90	66.0	1.9	662.279518	9.999617	4.0	4.0	0.470	8.6
2312	Sierra Leone	2000	Developing	39.0	533.0	29	3.97	20.395683	80.940461	3575	17.2	48	46.0	13.63	44.0	1.2	139.314773	4.564297	1.3	1.4	0.292	6.7
2311	Sierra Leone	2001	Developing	41.0	519.0	30	4.21	33.346915	80.940461	649	17.5	48	38.0	11.83	38.0	1.5	227.779471	4.739147	1.1	1.2	0.302	7.0
2309	Sierra Leone	2003	Developing	41.5	57.0	30	4.07	38.614732	80.940461	586	18.4	47	66.0	11.69	73.0	1.9	263.761831	5.199549	9.7	9.8	0.322	7.4
2308	Sierra Leone	2004	Developing	42.3	496.0	30	3.99	38.524548	80.940461	7	18.8	47	69.0	11.66	65.0	2.1	263.145817	5.439695	9.5	9.5	0.332	7.6
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
915	Finland	2014	Developing	89.0	78.0	0	8.80	6164.455402	80.940461	0	61.7	0	98.0	9.68	98.0	0.1	49914.618640	5.461512	0.9	0.8	0.890	17.0
1293	Italy	2004	Developed	89.0	66.0	2	8.98	4270.914882	96.000000	599	57.6	3	97.0	8.49	94.0	0.1	31174.561180	57.685327	0.5	0.5	0.846	15.6
241	Belgium	2014	Developed	89.0	76.0	0	12.60	7163.348923	98.000000	70	63.4	1	99.0	1.59	99.0	0.1	47439.396840	0.112957	1.0	1.0	0.890	16.3
2513	Sweden	2007	Developed	89.0	63.0	0	6.90	7593.391622	80.940461	1	56.1	0	98.0	8.92	98.0	0.1	53324.379370	0.914892	1.3	1.3	0.895	15.8
938	France	2007	Developing	89.0	89.0	3	12.20	64.737149	42.000000	39	58.6	3	99.0	1.45	98.0	0.1	416.583970	6.416229	0.6	0.6	0.873	16.1

	count	mean	std	min	25%	50%	75%	max
Status
Developed	512.0	79.197852	3.930942	69.9	76.8	79.25	81.7	89.0
Developing	2426.0	67.120177	8.988524	36.3	61.1	69.05	74.0	89.0

	count	mean	std	min	25%	50%	75%	max
world
3	289.0	54.450865	4.372468	44.0	51.7	55.5	58.0	60.0
2	1134.0	70.700088	4.407351	61.0	67.3	72.0	74.1	78.0
1	226.0	81.280088	2.693515	78.1	79.3	81.0	82.0	89.0

	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	BMI	under-five deaths	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
Year
2000	71.0	155.0	4	3.610000	35.661251	80.940461	47	37.9	5	88.0	5.50000	85.0	0.1	1451.297760	2884522.00	3.4	3.4	0.625000	11.500000
2001	71.2	151.0	4	3.810000	46.830275	80.940461	49	39.6	4	89.0	5.47000	89.0	0.1	1654.967610	3497124.00	3.3	3.3	0.627551	11.700000
2002	71.4	146.0	3	3.760000	49.735114	80.940461	36	42.0	4	91.0	5.52000	88.0	0.1	1631.417270	3522837.00	3.5	3.4	0.627551	11.900000
2003	71.1	144.0	3	4.040000	55.595439	80.940461	44	41.2	4	91.0	5.61000	91.0	0.1	2358.936290	3413852.00	3.3	3.3	0.627551	11.900000
2004	71.2	158.0	3	3.810000	55.361072	81.000000	22	41.3	4	91.0	5.70000	89.0	0.1	2351.338140	2586435.00	3.3	3.4	0.627551	11.992793
2005	71.6	138.0	3	4.140000	79.415027	87.000000	7	39.6	4	93.0	5.82000	93.0	0.1	2968.411860	3911914.00	3.4	3.5	0.637000	11.992793
2006	72.1	144.0	3	4.070000	76.198689	88.000000	15	43.0	4	94.0	5.70000	92.0	0.1	2892.522663	3779468.00	3.5	3.6	0.651000	12.100000
2007	72.4	136.0	3	4.130000	74.821749	89.000000	8	42.0	4	93.0	5.64000	93.0	0.1	2762.863540	3512932.00	3.5	3.4	0.661000	12.100000
2008	72.4	157.0	3	4.210000	93.367890	89.000000	4	43.2	4	93.0	5.76000	93.0	0.1	3385.696650	4491544.00	3.4	3.4	0.673000	12.200000
2009	72.6	147.0	3	4.070000	115.069242	92.000000	6	45.6	3	93.0	6.39000	93.0	0.1	3444.556600	2888584.00	3.4	3.3	0.686000	12.400000
2010	72.8	142.0	3	4.230000	129.226075	91.000000	17	44.2	3	94.0	5.86000	93.0	0.1	3453.487434	2877311.00	3.3	3.3	0.691000	12.500000
2011	73.3	139.0	3	4.090000	158.277080	92.000000	27	45.1	3	94.0	5.80000	94.0	0.1	4353.121392	3717672.00	3.3	3.3	0.700000	12.600000
2012	73.2	138.0	3	2.980000	196.915250	93.000000	11	45.7	3	94.0	6.12000	94.0	0.1	5659.382400	3863164.00	3.3	3.3	0.703000	12.700000
2013	72.8	141.0	2	2.420000	97.522115	93.000000	6	47.2	3	94.0	5.96000	94.0	0.1	4199.472530	5945747.00	3.3	3.3	0.700000	12.800000
2014	73.6	135.0	2	0.380000	151.104555	92.000000	13	47.0	3	94.0	5.88000	94.0	0.1	4429.657500	3973354.00	3.4	3.4	0.712000	12.900000
2015	73.9	138.0	2	4.602861	0.000000	92.000000	17	48.6	3	93.0	5.93819	93.0	0.1	4132.762920	5511976.68	3.5	3.4	0.718000	12.900000

	Country	Year	Status	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	...	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
2345	Slovenia	2015	Developed	88.0	74.0	0	4.602861	0.0	80.940461	18	...	95.0	5.93819	95.0	0.1	2729.863830	2.635310e+05	1.4	1.3	0.888000	17.300000
737	Denmark	2015	Developed	86.0	71.0	0	4.602861	0.0	80.940461	9	...	93.0	5.93819	93.0	0.1	5314.644160	5.683483e+06	1.1	0.9	0.923000	19.200000
673	Cyprus	2015	Developed	85.0	52.0	0	4.602861	0.0	97.000000	0	...	97.0	5.93819	97.0	0.1	2375.112700	1.169850e+05	1.0	1.0	0.854000	14.300000
544	Chile	2015	Developing	85.0	82.0	2	4.602861	0.0	97.000000	9	...	96.0	5.93819	96.0	0.1	13653.226400	1.776268e+07	0.8	0.8	0.845000	16.300000
1314	Japan	2015	Developed	83.7	55.0	2	4.602861	0.0	80.940461	35	...	99.0	5.93819	96.0	0.1	34474.137360	1.271410e+05	2.1	1.8	0.902000	15.300000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
432	Côte d'Ivoire	2015	Developing	53.3	397.0	57	4.602861	0.0	83.000000	65	...	81.0	5.93819	83.0	1.9	7483.158469	1.275338e+07	5.5	5.5	0.627551	11.992793
528	Chad	2015	Developing	53.1	356.0	46	4.602861	0.0	46.000000	418	...	52.0	5.93819	46.0	2.8	777.248751	1.494130e+05	8.5	8.4	0.394000	7.300000
512	Central African Republic	2015	Developing	52.5	397.0	15	4.602861	0.0	47.000000	150	...	47.0	5.93819	47.0	4.4	348.381417	4.546100e+04	8.2	8.2	0.347000	7.100000
48	Angola	2015	Developing	52.4	335.0	66	4.602861	0.0	64.000000	118	...	7.0	5.93819	64.0	1.9	3695.793748	2.785935e+06	8.3	8.2	0.531000	11.400000
2297	Sierra Leone	2015	Developing	51.0	413.0	22	4.602861	0.0	86.000000	607	...	86.0	5.93819	86.0	0.5	587.538233	7.237250e+05	7.4	7.3	0.431000	9.500000

	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	BMI	under-five deaths	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
Year
2000	10.295528	140.275938	149.285320	3.942625	1256.723594	21.032851	17776.459005	18.744158	209.636215	27.495075	2.104701	29.488424	6.973697	8479.444686	2.330784e+07	4.709447	4.969160	0.277808	3.993319
2001	10.189630	141.147685	148.416410	3.915644	1274.368926	21.967154	16100.646567	18.161368	201.890335	25.971137	2.055248	27.908500	7.034786	8234.335876	2.049691e+07	4.625413	4.885904	0.238668	3.562092
2002	10.062469	133.472330	141.030361	3.956564	1162.688712	22.036932	8591.234477	18.348250	194.206932	25.051564	2.137059	24.494670	7.002383	7925.486492	1.417078e+07	4.712128	4.833430	0.239612	3.559374
2003	10.127681	136.528282	140.246293	3.960509	1210.186804	24.737954	14067.930906	18.478674	186.571738	23.980408	2.157200	25.583139	6.927155	8468.267878	2.258137e+07	4.606450	4.739578	0.240497	3.529764
2004	10.126409	142.278928	133.027261	4.037282	1926.727421	23.707730	9688.322518	18.958261	179.170516	24.573983	2.258734	25.160880	6.737645	12463.071124	8.622615e+07	4.564903	4.677914	0.234434	3.428249

	Country	Year	Status	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	...	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
0	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
1	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
2	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
3	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
4	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2933	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
2934	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
2935	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
2936	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False
2937	False	False	False	False	False	False	False	False	False	False	...	False	False	False	False	False	False	False	False	False	False

	Year	Status	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	...	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling	Continent
0	15	1	65.0	263.0	62	0.01	71.279624	65.0	1154	...	8.16	65.0	0.1	584.259210	33736494.0	17.2	17.3	0.479	10.1	Asia
1	14	1	59.9	271.0	64	0.01	73.523582	62.0	492	...	8.18	62.0	0.1	612.696514	327582.0	17.5	17.5	0.476	10.0	Asia
2	13	1	59.9	268.0	66	0.01	73.219243	64.0	430	...	8.13	64.0	0.1	631.744976	31731688.0	17.7	17.7	0.470	9.9	Asia
3	12	1	59.5	272.0	69	0.01	78.184215	67.0	2787	...	8.52	67.0	0.1	669.959000	3696958.0	17.9	18.0	0.463	9.8	Asia
4	11	1	59.2	275.0	71	0.01	7.097109	68.0	3013	...	7.87	68.0	0.1	63.537231	2978599.0	18.2	18.2	0.454	9.5	Asia